MemFold: Learning Compact Soft Memory for Long-Context Personalization via On-Policy Optimization
MemFold trains fixed-size soft memory with on-policy rewards and leads PersonaMem personalization across Qwen backbones.
1 stories, newest first · one card per story
MemFold trains fixed-size soft memory with on-policy rewards and leads PersonaMem personalization across Qwen backbones.
Today 507 readers · 588 views · 463 reads · all time 158K views